HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shi, Zhiyuan, Qiu, Qibo, Xue, Feng, Jiang, Zhonglin, Yu, Li, Jiang, Jian, He, Xiaofei, Wang, Wenxiao
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.13684